Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add elimorals/jw-agent-toolkit --skill jw-apologeticsgit clone --depth 1 https://github.com/elimorals/jw-agent-toolkitWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/elimorals/jw-agent-toolkit/jw-apologetics)<a href="https://agentmods.dev/skills/elimorals/jw-agent-toolkit/jw-apologetics"><img src="https://agentmods.dev/badge/skills/elimorals/jw-agent-toolkit/jw-apologetics/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/elimorals/jw-agent-toolkit/jw-apologetics"><img src="https://agentmods.dev/badge/skills/elimorals/jw-agent-toolkit/jw-apologetics.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00072 | $0.00567 |
| Opus 5 | $0.00036 | $0.00283 |
| Sonnet 5 | $0.00014 | $0.00113 |
| Haiku 4.5 | $0.00007 | $0.00057 |
Grade A, and why
jw-apologetics scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
JW apologetics (verified citations)
Call the MCP tool apologetics(question, language="E", topic_top_k=1, web_top_k=3, use_rag=True).
Source priority of the findings returned (use this for ranking in your synthesis):
topic_index— Watch Tower Publications Index subject. The most authoritative source. If a finding hasmetadata.source == "topic_index"or"topic_index_entry", surface its citation first.question_refs— Bible references the user named.verse_text— actual verse text fetched from wol.jw.org.study_note— nwtsty commentary mapped to the verse.cdn_search— articles found via search.rag— local corpus (if anything is indexed).
How to compose the answer
- Open with the JW position — usually derived from a
topic_subjectortopic_subheadingfinding. Quoteexcerptif non-empty. - Back it with scripture — pull from
question_refs/verse_text/study_notefindings. Quote the verse text verbatim and cite thecitation.url. - Cite jw.org articles — for each
cdn_searchfinding, name the article title (citation.title) and linkcitation.url. - Never paraphrase doctrine from training data without a backing citation. If no citation exists, say so explicitly.
Boundaries
- For prep of a specific Watchtower Study, use
jw-meeting-prep. - For a single verse, use
jw-verse-lookup. - This skill is for defending and explaining JW positions using authoritative sources. It is not for personal opinion synthesis.
Example
User: "¿Qué dice la Biblia sobre la Trinidad?"
→ Call apologetics("¿Qué dice la Biblia sobre la Trinidad?", language="S").
→ The Trinity subject (185 subheadings, 563 citations) returns first.
→ Open with the JW position, quote 1Ti 2:5 / Juan 17:3 from the findings,
cite ti (Should You Believe in the Trinity?) and recent w articles.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 48 lines · 72 tokens per session scan A b6ead264cef0
jw-apologetics is a skill published in the GitHub repository elimorals/jw-agent-toolkit (5 stars, last pushed 25d ago), licensed Apache-2.0. It adds 72 tokens to every session and 567 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
memobase
A Russian-language skill for searching a local knowledge base built from documents and other sources such as web pages, YouTube, audio, and Obsidian notes.
harbor-clerk
Search and read documents from a local Harbor Clerk knowledge base. Use when the user references their personal documents, contracts, notes, emails, or asks "what did I store about X?".
simplicio-learn
Persist what a run taught you so the next run is cheaper and more correct — mine high-signal lessons from the trajectory, dedup them, and write them back to AGENTS.md / memory so they're applied not re-derived. Use after a run or at session end, when the user says "remember this", "do a retrospective", "learn from…
canvas
Fetch Canvas LMS courses and assignments via API token.
hr-onboarding
A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".
llama-factory
Expert guidance for fine-tuning LLMs with LLaMA-Factory - WebUI no-code, 100+ models, 2/3/4/5/6/8-bit QLoRA, multimodal support.